ElevenLabs Eleven-V3 Timing converts text to natural speech and returns alignment metadata—character/word timestamps in JSON—for precise subtitles, karaoke effects, and lip-sync. Supports voice_id, similarity/stability, and optional Speaker Boost. Priced at $0.10 per 1,000 characters. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.
Bezczynny
{
"audio": "https://d1q70pf5vjeyhc.cloudfront.net/predictions/1298dfeb67a04c7fa1bac264734c41a9/1.mp3",
"alignment": {
"characters": [
"W",
"e",
"l",
"c",
"o",
"m",
"e",
" ",
"t",
"o",
" ",
"o",
"u",
"r",
" ",
"a",
"d",
"v",
"a",
"n",
"c",
"e",
"d",
" ",
"t",
"e",
"x",
"t",
"-",
"t",
"o",
"-",
"s",
"p",
"e",
"e",
"c",
"h",
" ",
"s",
"y",
"s",
"t",
"e",
"m",
"!",
" ",
"E",
"x",
"p",
"e",
"r",
"i",
"e",
"n",
"c",
"e",
" ",
"h",
"i",
"g",
"h",
"-",
"q",
"u",
"a",
"l",
"i",
"t",
"y",
" ",
"v",
"o",
"i",
"c",
"e",
" ",
"s",
"y",
"n",
"t",
"h",
"e",
"s",
"i",
"s",
" ",
"w",
"i",
"t",
"h",
" ",
"n",
"a",
"t",
"u",
"r",
"a",
"l",
" ",
"p",
"r",
"o",
"n",
"u",
"n",
"c",
"i",
"a",
"t",
"i",
"o",
"n",
" ",
"a",
"n",
"d",
" ",
"c",
"l",
"e",
"a",
"r",
" ",
"a",
"r",
"t",
"i",
"c",
"u",
"l",
"a",
"t",
"i",
"o",
"n",
"."
],
"character_end_times_seconds": [
0.045,
0.09,
0.135,
0.18,
0.225,
0.27,
0.315,
0.368,
0.421,
0.474,
0.514,
0.554,
0.594,
0.634,
0.705,
0.776,
0.847,
0.918,
0.989,
1.06,
1.131,
1.202,
1.273,
1.369,
1.465,
1.561,
1.657,
1.753,
1.806,
1.859,
1.912,
1.952,
1.992,
2.056,
2.12,
2.184,
2.248,
2.312,
2.38,
2.448,
2.516,
2.584,
2.652,
2.72,
2.788,
2.868,
2.962,
3.056,
3.15,
3.244,
3.338,
3.432,
3.526,
3.62,
3.714,
3.808,
3.902,
3.95,
3.998,
4.046,
4.094,
4.142,
4.192,
4.242,
4.292,
4.342,
4.392,
4.442,
4.492,
4.542,
4.595,
4.648,
4.701,
4.754,
4.807,
4.86,
4.932,
5.004,
5.076,
5.148,
5.22,
5.292,
5.364,
5.436,
5.508,
5.58,
5.628,
5.676,
5.724,
5.772,
5.82,
5.87,
5.92,
5.97,
6.02,
6.07,
6.12,
6.17,
6.22,
6.288,
6.356,
6.424,
6.492,
6.56,
6.628,
6.696,
6.764,
6.832,
6.9,
6.968,
7.036,
7.104,
7.172,
7.272,
7.372,
7.472,
7.572,
7.625,
7.678,
7.731,
7.784,
7.837,
7.89,
7.97,
8.05,
8.13,
8.21,
8.29,
8.37,
8.45,
8.53,
8.61,
8.69,
8.77,
8.85,
8.93,
9.09
],
"character_start_times_seconds": [
0,
0.045,
0.09,
0.135,
0.18,
0.225,
0.27,
0.315,
0.368,
0.421,
0.474,
0.514,
0.554,
0.594,
0.634,
0.705,
0.776,
0.847,
0.918,
0.989,
1.06,
1.131,
1.202,
1.273,
1.369,
1.465,
1.561,
1.657,
1.753,
1.806,
1.859,
1.912,
1.952,
1.992,
2.056,
2.12,
2.184,
2.248,
2.312,
2.38,
2.448,
2.516,
2.584,
2.652,
2.72,
2.788,
2.868,
2.962,
3.056,
3.15,
3.244,
3.338,
3.432,
3.526,
3.62,
3.714,
3.808,
3.902,
3.95,
3.998,
4.046,
4.094,
4.142,
4.192,
4.242,
4.292,
4.342,
4.392,
4.442,
4.492,
4.542,
4.595,
4.648,
4.701,
4.754,
4.807,
4.86,
4.932,
5.004,
5.076,
5.148,
5.22,
5.292,
5.364,
5.436,
5.508,
5.58,
5.628,
5.676,
5.724,
5.772,
5.82,
5.87,
5.92,
5.97,
6.02,
6.07,
6.12,
6.17,
6.22,
6.288,
6.356,
6.424,
6.492,
6.56,
6.628,
6.696,
6.764,
6.832,
6.9,
6.968,
7.036,
7.104,
7.172,
7.272,
7.372,
7.472,
7.572,
7.625,
7.678,
7.731,
7.784,
7.837,
7.89,
7.97,
8.05,
8.13,
8.21,
8.29,
8.37,
8.45,
8.53,
8.61,
8.69,
8.77,
8.85,
8.93
]
},
"normalized_alignment": {
"characters": [
"W",
"e",
"l",
"c",
"o",
"m",
"e",
" ",
"t",
"o",
" ",
"o",
"u",
"r",
" ",
"a",
"d",
"v",
"a",
"n",
"c",
"e",
"d",
" ",
"t",
"e",
"x",
"t",
"-",
"t",
"o",
"-",
"s",
"p",
"e",
"e",
"c",
"h",
" ",
"s",
"y",
"s",
"t",
"e",
"m",
"!",
" ",
"E",
"x",
"p",
"e",
"r",
"i",
"e",
"n",
"c",
"e",
" ",
"h",
"i",
"g",
"h",
"-",
"q",
"u",
"a",
"l",
"i",
"t",
"y",
" ",
"v",
"o",
"i",
"c",
"e",
" ",
"s",
"y",
"n",
"t",
"h",
"e",
"s",
"i",
"s",
" ",
"w",
"i",
"t",
"h",
" ",
"n",
"a",
"t",
"u",
"r",
"a",
"l",
" ",
"p",
"r",
"o",
"n",
"u",
"n",
"c",
"i",
"a",
"t",
"i",
"o",
"n",
" ",
"a",
"n",
"d",
" ",
"c",
"l",
"e",
"a",
"r",
" ",
"a",
"r",
"t",
"i",
"c",
"u",
"l",
"a",
"t",
"i",
"o",
"n",
"."
],
"character_end_times_seconds": [
0.045,
0.09,
0.135,
0.18,
0.225,
0.27,
0.315,
0.368,
0.421,
0.474,
0.514,
0.554,
0.594,
0.634,
0.705,
0.776,
0.847,
0.918,
0.989,
1.06,
1.131,
1.202,
1.273,
1.369,
1.465,
1.561,
1.657,
1.753,
1.806,
1.859,
1.912,
1.952,
1.992,
2.056,
2.12,
2.184,
2.248,
2.312,
2.38,
2.448,
2.516,
2.584,
2.652,
2.72,
2.788,
2.868,
2.962,
3.056,
3.15,
3.244,
3.338,
3.432,
3.526,
3.62,
3.714,
3.808,
3.902,
3.95,
3.998,
4.046,
4.094,
4.142,
4.192,
4.242,
4.292,
4.342,
4.392,
4.442,
4.492,
4.542,
4.595,
4.648,
4.701,
4.754,
4.807,
4.86,
4.932,
5.004,
5.076,
5.148,
5.22,
5.292,
5.364,
5.436,
5.508,
5.58,
5.628,
5.676,
5.724,
5.772,
5.82,
5.87,
5.92,
5.97,
6.02,
6.07,
6.12,
6.17,
6.22,
6.288,
6.356,
6.424,
6.492,
6.56,
6.628,
6.696,
6.764,
6.832,
6.9,
6.968,
7.036,
7.104,
7.172,
7.272,
7.372,
7.472,
7.572,
7.625,
7.678,
7.731,
7.784,
7.837,
7.89,
7.97,
8.05,
8.13,
8.21,
8.29,
8.37,
8.45,
8.53,
8.61,
8.69,
8.77,
8.85,
8.93,
9.09
],
"character_start_times_seconds": [
0,
0.045,
0.09,
0.135,
0.18,
0.225,
0.27,
0.315,
0.368,
0.421,
0.474,
0.514,
0.554,
0.594,
0.634,
0.705,
0.776,
0.847,
0.918,
0.989,
1.06,
1.131,
1.202,
1.273,
1.369,
1.465,
1.561,
1.657,
1.753,
1.806,
1.859,
1.912,
1.952,
1.992,
2.056,
2.12,
2.184,
2.248,
2.312,
2.38,
2.448,
2.516,
2.584,
2.652,
2.72,
2.788,
2.868,
2.962,
3.056,
3.15,
3.244,
3.338,
3.432,
3.526,
3.62,
3.714,
3.808,
3.902,
3.95,
3.998,
4.046,
4.094,
4.142,
4.192,
4.242,
4.292,
4.342,
4.392,
4.442,
4.492,
4.542,
4.595,
4.648,
4.701,
4.754,
4.807,
4.86,
4.932,
5.004,
5.076,
5.148,
5.22,
5.292,
5.364,
5.436,
5.508,
5.58,
5.628,
5.676,
5.724,
5.772,
5.82,
5.87,
5.92,
5.97,
6.02,
6.07,
6.12,
6.17,
6.22,
6.288,
6.356,
6.424,
6.492,
6.56,
6.628,
6.696,
6.764,
6.832,
6.9,
6.968,
7.036,
7.104,
7.172,
7.272,
7.372,
7.472,
7.572,
7.625,
7.678,
7.731,
7.784,
7.837,
7.89,
7.97,
8.05,
8.13,
8.21,
8.29,
8.37,
8.45,
8.53,
8.61,
8.69,
8.77,
8.85,
8.93
]
}
}$0.1za uruchomienie·~10 / $1
PrzykładyZobacz wszystkie
Powiązane modele
README
ElevenLabs — Eleven V3 TTS with Alignment
Eleven V3 (Alignment) turns text into natural speech and, at the same time, returns precise timing data for every character and word. You get an audio file plus alignment metadata, so you can drop the voice straight onto a timeline for subtitles, karaoke, lip-sync and fine-grained editing.
🎧 What this model does
- Generates high-quality speech with natural pronunciation, pacing and intonation.
- Returns alignment metadata with per-character / per-word timestamps (start–end in seconds).
- Makes it easy to build auto-subtitles, word-highlighting, reading trainers, talking avatars and precise dubbing tools.
Compared with a normal TTS model (audio only), this version also outputs an alignment object containing, for example:
- a list of characters or words
- corresponding end times in seconds (and, where available, start times)
so the text and audio are tightly locked to each other.
🧩 Typical uses
- Automatic subtitle generation with timecodes (SRT / VTT).
- Word-by-word highlighting or karaoke-style lyrics.
- Lip-sync for digital humans or 2D/3D characters driven by word/phoneme timing.
- Precise VO replacement and edit point detection inside existing videos.
- Language-learning apps: follow-along reading, shadowing and pronunciation practice.
🔧 Input parameters
-
text (required) – Script to be spoken. Recommended up to 5,000 characters per call.
-
voice_id (required) – Which Eleven voice to use (for example: Alice, Elli, George).
-
Full voice list to find your voice_id.
-
similarity (0–1) – How closely the output should match the base voice’s timbre and style.
-
stability (0–1) – Higher values give more consistent delivery; lower values allow more expressive variation.
-
use_speaker_boost (bool) – English text normalisation that improves numbers, dates and measurements.
📤 Output format
Each run returns:
-
audio – URL of the generated audio file (MP3).
-
alignment – JSON metadata including:
-
list of characters and/or words in order
-
corresponding timing arrays (for example character_end_times_seconds) with values in seconds
You can parse this metadata to:
- build subtitles with exact in/out times
- drive on-screen highlighting in sync with the audio
- control animation, lip-sync or visual effects based on specific words
💰 Pricing
Billing is based on the length of the input text.
- Base rate: 0.10 USD per 1,000 characters
- The character count is rounded up to the next 1,000 characters. Input less than 1000 characters will be charged as 1000 characters.
Anything below 1,000 characters is still billed as one full 1,000-character block.
🚀 How to use
- Fill text with your script.
- Select a voice_id from the supported ElevenLabs voices.
- Optionally tune similarity, stability, and enable use_speaker_boost for English number-heavy content.
- Run the request.
- Download the audio file and read the alignment JSON to build subtitles, highlights or animation timing.
📝 Notes and tips
- Punctuation matters: clear sentence boundaries improve rhythm and alignment accuracy.
- For very long scripts, split them into several calls if you need section-level control on the timeline.
- If you see errors like “invalid voice id”, cross-check with the most recent voice list and update the parameter value.
- When building players or editors, always treat the alignment timings (in seconds) as the single source of truth for where each character or word should appear.
Eleven v3 Timing API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/elevenlabs/eleven-v3/timing with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Eleven v3 Timing below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/elevenlabs/eleven-v3/timing" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"text": "Welcome to our advanced text-to-speech system! Experience high-quality voice synthesis with natural pronunciation and clear articulation.",
"voice_id": "Alice",
"similarity": 1,
"stability": 0.5,
"use_speaker_boost": true
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("elevenlabs/eleven-v3/timing", {
"text": "Welcome to our advanced text-to-speech system! Experience high-quality voice synthesis with natural pronunciation and clear articulation.",
"voice_id": "Alice",
"similarity": 1,
"stability": 0.5,
"use_speaker_boost": true
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"elevenlabs/eleven-v3/timing",
{
"text": "Welcome to our advanced text-to-speech system! Experience high-quality voice synthesis with natural pronunciation and clear articulation.",
"voice_id": "Alice",
"similarity": 1,
"stability": 0.5,
"use_speaker_boost": true
}
)
print(output["outputs"][0]) # → URL of the generated outputEleven v3 Timing API — Frequently asked questions
What is the Eleven v3 Timing API?
Eleven v3 Timing is a ElevenLabs model for audio generation, exposed as a REST API on WaveSpeedAI. ElevenLabs Eleven-V3 Timing converts text to natural speech and returns alignment metadata—character/word timestamps in JSON—for precise subtitles, karaoke effects, and lip-sync. Supports voice_id, similarity/stability, and optional Speaker Boost. Priced at $0.10 per 1,000 characters. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Eleven v3 Timing API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/elevenlabs/elevenlabs-eleven-v3-timing.
How much does Eleven v3 Timing cost per run?
Eleven v3 Timing starts at $0.10 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Eleven v3 Timing accept?
Key inputs: `similarity`, `stability`, `text`, `use_speaker_boost`, `voice_id`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/elevenlabs/elevenlabs-eleven-v3-timing.
How long does Eleven v3 Timing take to generate?
Average end-to-end generation time on WaveSpeedAI is around 39 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Eleven v3 Timing outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (ElevenLabs). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.